[feat] Adding Metaformer support #294
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
the
CLA Signed
blefaudeux
force-pushed
the
poolformer
branch
2 times, most recently
from
9820481
to
93ec973
Compare
Codecov Report
@@ Coverage Diff @@
## main #294 +/- ##
==========================================
+ Coverage 92.80% 92.95% +0.14%
==========================================
Files 64 65 +1
Lines 3489 3519 +30
==========================================
+ Hits 3238 3271 +33
+ Misses 251 248 -3
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
blefaudeux
force-pushed
the
poolformer
branch
3 times, most recently
from
70a3c7d
to
7a96bc3
Compare
|
the coverage numbers should be fixed by the PR update, it's now properly tested |
blefaudeux
force-pushed
the
poolformer
branch
8 times, most recently
from
327f447
to
550cff9
Compare
dianaml0
approved these changes
May 9, 2022
|
|
||
| ### MicroMetaformer | ||
|
|
||
| This is very close to the MicroViT example above, but illustrating the use of a hierarchical Transformer ([Metaformer](https://arxiv.org/pdf/2111.11418.pdf)) this time, through a helper function which generates the required configuration given the pooling parameters. The suggested configuration is about 6.6M parameters big (half of a ResNet18) and trains to about 86% top-1 Cifar10 within minutes. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Add a helper to generate a Metaformer config, and add an example to train it on Cifar10. Add some documentation about it
TODO
Before submitting
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.